Find research datasets worth reusing

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 13. School girl presenting Vădastra School's Facebook page

In order to achieve the third educational level, we experimented the social media tools, i.e. the project’s Google+ educational blog, by posting information complementary to that available on the Time Maps website, and also thematic questionnaires to foster a question-answer (Q&A) learning style. This allowed us to monitor and evaluate the information retention. In this stage we encountered the challenge to stimulate children and teachers to continue using our learning system, by posting new educational content, announcements and social messages. After a period of experimentation we proceeded to a statistical evaluation of children’s answers, which is presented in the next section.

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 7. The projects's Twitter page for educational and research micro-blogging

The fourth stage was the use of social media to build a social learning network based on content and experience sharing and creation. The following web 2.0 services were used as a distributed platform able to support our experimental learning system: a) Panoramio (http://www.panoramio.com/user/7606828) (Figure 6) as a geo-referenced photo-sharing service over Google Maps and Google Earth for sharing project’s essential results; b) Twitter (https://twitter.com/maps_of_time) (Figure 7), as a social network and micro-blogging service for short announcements and comments; c) Google+ (https://plus.google.com/114705936110835992130?hl=en#114705936110835992130/posts?hl=en) (Figure 8), as a platform for sharing and tagging multiple content (photo, video), blogging and video chatting service with the recent Google Hangout, for sharing educational content; d) Google Drive (Levin, 2013) for cloud storage and collaborative document editing. We also created a YouTube channel for public distribution of video content (https://www.youtube.com/TimemapsNet), (Rusu et al., 2013) and a Facebook page of Vădastra School (https://www.facebook.com/scoalaVădastra).

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 6. Virtual Space on Panoramio+ with the experiments carried in Vădastra village

opencc-by-4.0Feb 2018View details →

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 1. An experiment of building a prehistoric house, carried out by Professor Dragoş Gheorghiu in Vădastra

The learning experiment in Vădastra village began by geo-referencing some points of interest in the archaeological area (Gheorghiu & Stefan, 2013a; 2013b), which were identified from the archaeological published materials and from information provided by the villagers, as well as resulting from fieldwork conducted for over a decade (i.e. archaeological experimentation) in this village (Gheorghiu, 2001; 2008). The geographic data (POIs) was collected on the archaeological site by the K-12 children under the coordination of a project team member from the National University of Arts Bucharest (NUA).

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 2. An experiment with sunken up-draught kilns, carried out by Professor Dragoş Gheorghiu in Vădastra

The second stage was represented by the physical reconstruction at real scale of a prehistoric house and of a corner of a Roman villa rustica, designed and coordinated by Professor Dragoş Gheorghiu. In these physical reconstructions video recordings and photo shoots were produced by specialist members of the project team, in order to be used later as augmentations in the AR application and for distribution by means of SNS.

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 4. Augmented Reality with video movie and social media (a vertical loom in front of two reconstructed kilns and a wall of a Roman villa rustica)

The third stage was represented by the 3D virtual reconstruction process of the historical contexts, in our case a prehistoric village and a complete Roman villa rustica, with the help of students from the Design Department, NUA, coordinated by Professor Arch. Andreea Hasnaş. The AR application was created and tested on two commercial AR platforms, Layar and Junaio, and recently moved on the Aurasma platform (https://www.aurasma.com/). The POIs were augmented with the 3D virtual reconstructions, and also with 2D images and videos representing 3D virtual tours and technological processes (Figures 3, 4, 5). The AR application was connected to teachers’ emails and to Twitter, Facebook and Google+ project’s pages.

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 9.The educational blog on Google+ Time Maps page–the weaving techniques

For this subject two video films were posted on Google+ (a performance and a 3D reconstruction), slightly different from those available on the Time Maps web site, but containing the same information. The children had to make a little effort to relate this information with the one presented on the site, to make a connection between the questions, the fragments from videos at which the answers referred to and the information from the site. The set of questionnaires lead the school children through the majority of data offered by the web site regarding to the two historical periods (Figures 9, 10).

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 3. Augmented Reality with archaeological stratigraphy (a prehistoric house and a Roman villa reconstructed in 3D)

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 15. Social media visits

We also point out the following the advantages of Google+: - Google+ is a more user-friendly than other social environments and very suitable for use by school children than other blogging environments (e.g. Wordpress); thus it stimulated the play-like learning. - Google+ is more customizable than other social environments; - By allowing teachers to post questionnaires and to share images and videos or links to content on the Time Maps website, the Google+ page acted as an aggregator of information and a for scaffolding the learning process. After different stages of experimentation, we produced different statistical analysis of our results: concerning the most accessed social media. It indicated that Panoramio was the most visited (Figure 15) The statistics indicate that the different social networks had different levels of impact on the children and that in the future developments the focus should be on those more frequently accessed.

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 8. Virtual social space on Google+

For micro-blogging we hashtagged the main topic as #maps_of_time and created keywords related to three ancient technologies specific for the studied contexts (textiles, glass, ceramics) to facilitate a categorization of the topics and their retrieval. To achieve a unified and coherent platform, the personal spaces of the social networks were customized with logos and landing pages, designed by Associate Professor Marina Theodorescu (NUA).

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 14. The survey as a public posting on Google+ Time Maps page

During this experimentation phase a symposium was organized at Vădastra School with the purpose to present our learning experiment to a group of 30 teachers from the Olt County. An open history lesson on the Time Maps web site was held by a history teacher, and a school girl described the Facebook page of the Vădastra School (Figure13), maintained by both teachers and children. The invited teachers gave a feedback on the effectiveness and utility of the Time Maps learning system by responding to a questionnaire-based survey, which was posted on the Google+ page (Figure 14).

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 10. The educational blog on Google+ Time Maps page – the glass manufacturing techniques

For this subject two video films were posted on Google+ (a performance and a 3D reconstruction), slightly different from those available on the Time Maps web site, but containing the same information. The children had to make a little effort to relate this information with the one presented on the site, to make a connection between the questions, the fragments from videos at which the answers referred to and the information from the site. The set of questionnaires lead the school children through the majority of data offered by the web site regarding to the two historical periods (Figures 9, 10).

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 5. Fiber artist Alexandra Rusu (NUA) working at a Roman vertical loom (video movie)

BRAIN Journal-Participative Teaching with Mobile Devices and Social Networks for K-12 Children-Figure 11. Children applying weaving techniques under the control of the staff from NUA Bucharest

The information from a) and b) has been used by other colleagues in the local school and in the future will be used by other schools in the country or abroad. This represented the second educational level of the project, i.e. the analysis of the collected data. Information from c) was further analyzed by university teachers, filtered and added as an enhancement to the content of the AR platform. An example of user-created content are the movies made with smartphone cameras, recording the children2 while performing traditional crafts (Figures 11, 12).

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 11.Weka Results for Images

The dataset of the real images is also treated the same way as the dataset of the sketches. Total tree images used = 86 Total car images used = 54 Learning rate = 0.3 Momentum = 0.2 Number of epochs = 500 70% of data is used to train the neural network and the remaining 30% is used for testing the trained neural network. Figure 10 shows the neural network for images. The results are shown in Figure 11 and are as follows: Total Correct Recognition = 83.7838% Total Incorrect Recognition = 16.2162% Error Per epoch = 0.0235851

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 8. Training Neural Network for Sketches

It is described in the previous section that a mobile application is used to collect data about the sketches and the data is converted to 20x20=400 integer numbers to give it as input to Weka. Our experimentation includes only two objects for recognition i.e. trees and cars. Total tree sketches used = 175 Total car sketches used = 72 Learning rate = 0.3 Momentum = 0.2 Number of epochs = 500 70% of data is used to train the neural network and the remaining 30% is used for testing the trained neural network. Figure 8 shows the neural network for sketches. The results are shown in Figure 9 and are as follows: Total Correct Recognition = 100%

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 5. Cropped Sketch

Figure 5 shows the interface of the mobile application that is created to collect the data of the sketches. It contains a drawing canvas; where drawings are made and it also contains few text boxes which are filled with the information of the drawing. For example, if the drawing is a tree, ‘1’ is written in the tree text box. Furthermore, the undo and redo buttons help modify the drawing and the clear button clears everything drawn onto the drawing canvas.  The drawing of a tree is shown on the drawing canvas in Figure 4. It is clear from the figure that there is some empty area on top, right, left and bottom of the drawing sketch, which can cause problems while using this image for training the neural network. Therefore, there is implemented a crop function which crops the image very minutely and removes the empty space as shown in Figure 5.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 4. Mobile Application to collect Sketch data

The drawing of a tree is shown on the drawing canvas in Figure 4. It is clear from the figure that there is some empty area on top, right, left and bottom of the drawing sketch, which can cause problems while using this image for training the neural network.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 3. The used methodology

The training process we use in both trainings is based on neural networks, using the backpropgation algorithm. By using this algorithm, we are going to finally obtain the weights that will be used in our model to make the system recognize the input given by the user.  Once the training for the hand drawn sketches is over, we are going to get weights that will be used to recognize any inputted hand drawn sketches. For example, if the user draws a tree, the system will be able to recognize what has been drawn as a tree, using the obtained weights from the neural networks. On the other hand, once the training for the real images is over, it means that if we provide our system with a real image, for example a tree, the system will be able to recognize it using the obtained weights from the training phase.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 6. Reducing size of Sketch

As previously described, there are a total of 1600 integers, which can be the input to the dataset for neural networks. But it is a huge number, so in order to minimize the size of inputs to the neural network the 40x40 matrix is reduced to 20x20 by skipping odd rows and columns of the original matrix. Figure 6 shows a matrix containing green and red rows and columns. If this was the 40x40 matrix, then the red part of this matrix would be skipped to convert it into a 20x20 sized matrix. Now there are only 20x20=400 values, which is a reasonable input size for the neural network.  The other part of the developed approach is to collect the data about the same two objects of the real pictures taken by the camera. These images are converted into black and white pictures and then treated the same way as the sketches, i.e. black and white pictures are also converted into integers based on the color of each pixel.